# Search Across Metadata

## Why Search Matters

Locating the right data asset in large enterprises often feels like searching for a needle in a haystack. Business users may not be familiar with schema names or column structures, while analysts spend a significant amount of time manually mapping objects. Traditional search tools rely on exact keywords and return long, unrefined lists that require further interpretation.

**askEdgi** simplifies this process by interpreting natural language queries and returning context-aware results. Instead of focusing only on technical matches, it understands business intent and retrieves relevant metadata across the platform.

### What Can Be Searched

askEdgi supports natural language search across multiple metadata domains, including:

* **Data Catalog:** Tables, columns, schemas, and files
* **Business Glossary**: Terms, categories, and subcategories
* **Projects**: Ongoing Projects in the organisation
* **Service Desk Template:** Active service desk templates 

**Please refer to the following Document on what can be searched using Edgi**

* [Discovery and Analytics Mode](https://docs.ovaledge.com/ai/askedgi-prompts#discovery-and-analytics-mode)

### Predefined Prompt Library

The workspace features a predefined set of AI prompts for quick interaction and discovery.

**Examples**

* What can you do?
* Where is my sales data?
* Find a dataset that helps me calculate the highest average air temperature in the US?

<figure><img src="https://1813356899-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FhTnkoJQml0pok9awFDhx%2Fuploads%2FmiHA24Xt2HPVMzrDaHA5%2Funknown.png?alt=media&#x26;token=ca9d563b-e801-4896-ad0c-66cedaf42dd0" alt=""><figcaption></figcaption></figure>

Selecting any predefined prompt instantly triggers the AI assistant to perform the corresponding operation.

{% hint style="info" %}
Using simple, specific language in prompts helps generate more accurate and helpful responses. All conversations maintain their context until the thread is closed.
{% endhint %}

## **Use Case & Real-Life Scenario**

A newly onboarded marketing analyst is assigned the task of analyzing customer sentiment. Without prior knowledge of schemas or storage structures, the analyst enters the query:\
“Which tables contain customer feedback?”

**askEdgi immediately returns results such as:**

* customer\_reviews
* product\_feedback
* support\_comments

**Each result provides:**

* Object name and description
* Stewardship details
* Tags and associated terms
* Row count
* Data quality and curation scores
* Direct link to the summary page
* Option to add the object to the Workspace

The analyst continues with the query:&#x20;

“**What is the data quality score of the table customer\_reviews?**”

The askEdgi delivers data quality and curation scores, along with ownership and stewardship information. Within two queries, the analyst identifies the correct table, understands its context, and verifies compliance classifications - without writing SQL or browsing schemas.

**Example Searches**

* **Search Across Glossary**: Returns business terms, categories, and definitions.

  <figure><img src="https://1813356899-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FhTnkoJQml0pok9awFDhx%2Fuploads%2FPeTM5CuvAYtdsl0BgkpQ%2Fimage.png?alt=media&#x26;token=a803bd36-8890-4adf-9125-cbd0a83f2205" alt=""><figcaption></figcaption></figure>
* **Search Across Catalog**: Retrieves technical metadata, including tables, schemas, and columns.

  <figure><img src="https://1813356899-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FhTnkoJQml0pok9awFDhx%2Fuploads%2FMcDdb7q6CZS89EgMbzPB%2Fimage.png?alt=media&#x26;token=ab0e44ce-a1ae-48f5-9e10-e52f7255d9f1" alt=""><figcaption></figcaption></figure>

### Availability

* **Public** – Available (metadata search across catalog, glossary, tags, stories, and question wall).
* **SaaS** – Available (full metadata coverage).
* **On-Prem** – Limited to catalog search only (workspace analysis and enrichment unavailable).

## **Session Context and Security**

All workspace activities operate within a secure environment. Uploaded files, catalog integrations, and conversational interactions remain confined to the authenticated session.

Data is not transmitted externally or stored permanently beyond configured retention periods.

***

Copyright © 2025, OvalEdge LLC, Peachtree Corners, GA USA